ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuetao, Kuang, Zijia, Li, Ting, Hao, Qun, Yan, Zike, Zhou, Guyue, Zhang, Shaohui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911006852120576
author Li, Yuetao
Kuang, Zijia
Li, Ting
Hao, Qun
Yan, Zike
Zhou, Guyue
Zhang, Shaohui
author_facet Li, Yuetao
Kuang, Zijia
Li, Ting
Hao, Qun
Yan, Zike
Zhou, Guyue
Zhang, Shaohui
contents We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint selection, and path planning. The key to ActiveSplat is a hybrid map representation that integrates both dense information about the environment and a sparse abstraction of the workspace. Therefore, the system leverages sparse topology for efficient viewpoint sampling and path planning, while exploiting view-dependent dense prediction for viewpoint selection, facilitating efficient decision-making with promising accuracy and completeness. A hierarchical planning strategy based on the topological map is adopted to mitigate repetitive trajectories and improve local granularity given limited time budgets, ensuring high-fidelity reconstruction with photorealistic view synthesis. Extensive experiments and ablation studies validate the efficacy of the proposed method in terms of reconstruction accuracy, data coverage, and exploration efficiency. The released code will be available on our project page: https://li-yuetao.github.io/ActiveSplat/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21955
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting
Li, Yuetao
Kuang, Zijia
Li, Ting
Hao, Qun
Yan, Zike
Zhou, Guyue
Zhang, Shaohui
Robotics
Computer Vision and Pattern Recognition
We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint selection, and path planning. The key to ActiveSplat is a hybrid map representation that integrates both dense information about the environment and a sparse abstraction of the workspace. Therefore, the system leverages sparse topology for efficient viewpoint sampling and path planning, while exploiting view-dependent dense prediction for viewpoint selection, facilitating efficient decision-making with promising accuracy and completeness. A hierarchical planning strategy based on the topological map is adopted to mitigate repetitive trajectories and improve local granularity given limited time budgets, ensuring high-fidelity reconstruction with photorealistic view synthesis. Extensive experiments and ablation studies validate the efficacy of the proposed method in terms of reconstruction accuracy, data coverage, and exploration efficiency. The released code will be available on our project page: https://li-yuetao.github.io/ActiveSplat/.
title ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.21955